2 citations · 4 across the 13 of their papers we have counts for
5 papers · 1 filter
TEX-MEX: Similarity-Guided Temporal Contrastive Learning for Time Series
Aditya Radhakrishnan, Maxwell A. Xu, Wanting Mao +3
Contrastive learning for time series depends on deciding which pairs of inputs should be treated as similar and dissimilar. Because few augmentations reliably preserve meaning in t…
Variable Input Masked Autoencoders for Wrist-Worn Accelerometry
Harish Haresamudram, Wanting Mao, Aditya Radhakrishnan +2
Large-scale repositories of wearable sensor data have enabled the development of foundation models for human activities and behavior. However, existing models are pretrained using…
GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
Zechen Li, Keerthana Natarajan, Weizhi Zhang +11
Continuous glucose monitoring (CGM) provides a dense view of daily metabolic physiology, yet existing generic time-series and CGM-specific foundation models often encode glucose tr…
How Well Do Multimodal Models Reason on ECG Signals?
Maxwell A. Xu, Harish Haresamudram, Catherine W. Liu +11
While multimodal large language models offer a promising solution to the "black box" nature of health AI by generating interpretable reasoning traces, verifying the validity of the…
Bio-Inspired Self-Supervised Learning for Wrist-worn Accelerometer Data
Prithviraj Tarale, Kiet Chu, Abhishek Varghese +4
Wearable accelerometers enable large-scale health monitoring, yet learning robust human-activity representations has been constrained by scarce labeled data. While self-supervised…